Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Approach-level diversity in LLM mathematical reasoning captures strategic variation in problem-solving methods, revealing limitations of surface-level diversity metrics and highlig…

Hugging Face · Daily Papers ·Sangmook Lee, Minbeom Kim · ·▲ 10 upvotes

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Sangmook Lee, Minbeom Kim, Jeonghye Kim, Dohyung Kim, Sojeong Rhee, Kyomin Jung

  • 10 upvotes da comunidade
  • Temas: diversity-aware RLVR, LLM judge framework, approach-level diversity, surface-level variation, test-time scaling, policy optimization

Resumo

Resumo original (em inglês), extraído do paper:

Approach-level diversity in LLM mathematical reasoning captures strategic variation in problem-solving methods, revealing limitations of surface-level diversity metrics and highlighting challenges in directly optimizing diverse reasoning approaches.

Onde ler

compartilhar: